论文标题
使用对抗攻击传递性的神经体系结构的相似性
Similarity of Neural Architectures using Adversarial Attack Transferability
论文作者
论文摘要
近年来，为图像分类开发了许多深层神经体系结构。它们是相似的还是不同的，哪些因素会导致其（DIS）相似性。为了解决这个问题，我们旨在设计神经体系结构之间的定量且可扩展的相似性度量。我们从攻击转移性（SAT）中提出了相似性，即对抗攻击传递性包含与输入梯度和决策边界有关的信息，并广泛用于理解模型行为。我们使用我们提出的相似性函数对69个最先进的成像网分类器进行了大规模分析，以回答这个问题。此外，我们使用模型相似性观察到与神经体系结构相关的现象，模型多样性可以在特定条件下在模型集成和知识蒸馏上提高性能。我们的结果提供了有关为什么需要具有不同组成部分的不同神经体系结构的见解。
In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious. To address this question, we aim to design a quantitative and scalable similarity measure between neural architectures. We propose Similarity by Attack Transferability (SAT) from the observation that adversarial attack transferability contains information related to input gradients and decision boundaries widely used to understand model behaviors. We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers using our proposed similarity function to answer the question. Moreover, we observe neural architecture-related phenomena using model similarity that model diversity can lead to better performance on model ensembles and knowledge distillation under specific conditions. Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
